{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:53:06Z","timestamp":1785433986251,"version":"3.56.0"},"posted":{"date-parts":[[2026,7,1]]},"group-title":"Neuroscience","reference-count":37,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"name":"EU Horizon 2020","award":["964220"],"award-info":[{"award-number":["964220"]}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"crossref","award":["355407"],"award-info":[{"award-number":["355407"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/00ckakm23","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Research Council of Finland Flagship programme: Finnish Center for Artificial Intelligence FCAI"},{"DOI":"10.13039\/501100004155","name":"Magnus Ehrnrooth Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004155","id-type":"DOI","asserted-by":"crossref"}]},{"name":"UKRI Turing AI World\u2010Leading Researcher Fellowship","award":["EP\/W002973\/1"],"award-info":[{"award-number":["EP\/W002973\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>Individual brains are unique in structure and function. Functional differences are captured by neural fingerprints, which reflect individual differences in behavior and cognition as well as group-level changes related to neurodegenerative diseases. Most research efforts so far have focused on fingerprints com-prising full functional connectomes. However, the high dimensionality of the connectomes can increase computational load and impede performance of machine learning methods in potential applications. A low-dimensional alternative that retains individual features of the full connectomes would thus be beneficial. The present study employed latent-noise Bayesian Reduced Rank Regression (lnBRRR) to learn low-dimensional latent spaces that capture individual features in functional connectivity and power spectral density data derived from MEG recordings. LnBRRR performance was assessed with low training set sizes (N=20-44), and against principal component analysis and linear discriminant analysis. Model performance was also assessed with task data, and the solutions were compared across task conditions with cosine similarity to establish whether individual features are altered by different cognitive processes. LnBRRR captured generalizable individual patterns already at N=20 but N=30-35 was needed to reach optimal test accuracies and to prevent potential overfitting. The model also achieved comparable performance to the alternative models. Latent fingerprints derived from task data attained comparable performance to resting-state latent fingerprints, and lnBRRR solutions were shown to generalize across conditions. Additionally, the model solutions for power spectral density data were discovered to be notably similar, yet differently rotated, over task conditions, suggesting that similar patterns of individual features were captured by the model regardless of the task condition. Altogether, the present results highlight lnBRRR as a potential tool for neuroimaging data analysis and demonstrate that individual differences in power spectral density are largely intrinsic and unaffected by varying cognitive processes.<\/jats:p>","DOI":"10.64898\/2026.06.26.734424","type":"posted-content","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:40:11Z","timestamp":1782934811000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning on magnetoencephalography data yields generalizable low-dimensional neural fingerprints that distinguish individuals across task conditions"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3335-7551","authenticated-orcid":false,"given":"Joonas","family":"Karhula","sequence":"first","affiliation":[{"name":"Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7733-715X","authenticated-orcid":false,"given":"Anttoni","family":"Ojanper\u00e4","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University, Espoo, Finland"},{"name":"ELLIS Institute Finland, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9871-4700","authenticated-orcid":false,"given":"Ersin","family":"Y\u0131lmaz","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8638-0267","authenticated-orcid":false,"given":"Susanne","family":"Merz","sequence":"additional","affiliation":[{"name":"Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1925-9154","authenticated-orcid":false,"given":"Samuel","family":"Kaski","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University, Espoo, Finland"},{"name":"ELLIS Institute Finland, Espoo, Finland"},{"name":"Department of Computer Science, University of Manchester, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2499-193X","authenticated-orcid":false,"given":"Riitta","family":"Salmelin","sequence":"additional","affiliation":[{"name":"Department of Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026070321250822000_2026.06.26.734424v1.1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2873423"},{"key":"2026070321250822000_2026.06.26.734424v1.2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asr013"},{"issue":"5","key":"2026070321250822000_2026.06.26.734424v1.3","doi-asserted-by":"crossref","first-page":"056011","DOI":"10.1088\/1741-2552\/aacfe4","article-title":"Phase locking value revisited: teaching new tricks to an old dog","volume":"15","year":"2018","journal-title":"Journal of Neural Engineering"},{"key":"2026070321250822000_2026.06.26.734424v1.4","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neubiorev.2018.05.008","article-title":"The cingulum bundle: Anatomy, function, and dysfunction","volume":"92","year":"2018","journal-title":"Neuroscience & Biobehavioral Reviews"},{"key":"2026070321250822000_2026.06.26.734424v1.5","doi-asserted-by":"crossref","first-page":"120021","DOI":"10.1016\/j.neuroimage.2023.120021","article-title":"Task matters: Individual MEG signatures from naturalistic and neurophysiological brain states","volume":"271","year":"2023","journal-title":"NeuroImage"},{"issue":"1","key":"2026070321250822000_2026.06.26.734424v1.6","doi-asserted-by":"crossref","first-page":"5713","DOI":"10.1038\/s41467-021-25895-8","article-title":"Brief segments of neurophysiological activity enable individual differentiation","volume":"12","year":"2021","journal-title":"Nature Communications"},{"key":"2026070321250822000_2026.06.26.734424v1.7","doi-asserted-by":"crossref","first-page":"105201","DOI":"10.1016\/j.ebiom.2024.105201","article-title":"The neurophysiological brain-fingerprint of Parkinson\u2019s disease","volume":"105","year":"2024","journal-title":"eBioMedicine"},{"issue":"1","key":"2026070321250822000_2026.06.26.734424v1.8","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"2026070321250822000_2026.06.26.734424v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103748"},{"key":"2026070321250822000_2026.06.26.734424v1.10","doi-asserted-by":"crossref","unstructured":"Duong-Tran, D. , Magsino, M. , Goni, J., and Shen, L. (2024). Preserving Human Large-Scale Brain Con-nectivity Fingerprint Identifiability with Random Projections. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pages 1\u20135, Athens, Greece. IEEE.","DOI":"10.1109\/ISBI56570.2024.10635372"},{"key":"2026070321250822000_2026.06.26.734424v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4135"},{"key":"2026070321250822000_2026.06.26.734424v1.12","doi-asserted-by":"crossref","unstructured":"Gelman, A. , Carlin, J. , Stern, H. , Dunson, D. , Vehtari, A. , and Rubin, D. (2013). Bayesian Data Analysis. CreateSpace, United States, 3rd ed edition.","DOI":"10.1201\/b16018"},{"key":"2026070321250822000_2026.06.26.734424v1.13","first-page":"1","article-title":"Multiple Output Regression with Latent Noise","volume":"17","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"2026070321250822000_2026.06.26.734424v1.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2018.03.035"},{"key":"2026070321250822000_2026.06.26.734424v1.15","doi-asserted-by":"crossref","unstructured":"Guichet, C. , Harquel, S. , Achard, S. , Mermillod, M. , and Baciu, M . (2025). Lifespan oscillatory dynamics in lexical production: A population-based MEG resting-state analysis. Imaging Neuroscience, 3:imag a 00551.","DOI":"10.1162\/imag_a_00551"},{"key":"2026070321250822000_2026.06.26.734424v1.16","doi-asserted-by":"publisher","DOI":"10.1111\/ejn.16292"},{"issue":"1","key":"2026070321250822000_2026.06.26.734424v1.17","doi-asserted-by":"crossref","first-page":"e1013931","DOI":"10.1371\/journal.pcbi.1013931","article-title":"Capturing individual variation in children\u2019s electroencephalograms during nREM sleep","volume":"22","year":"2026","journal-title":"PLOS Computational Biology"},{"key":"2026070321250822000_2026.06.26.734424v1.18","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0193(1999)8:4<194::AID-HBM4>3.0.CO;2-C"},{"key":"2026070321250822000_2026.06.26.734424v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.05.056"},{"key":"2026070321250822000_2026.06.26.734424v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24454"},{"issue":"2","key":"2026070321250822000_2026.06.26.734424v1.21","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1027\/1614-2241.2.2.57","article-title":"Tucker\u2019s Congruence Coefficient as a Meaningful Index of Factor Similarity","volume":"2","year":"2006","journal-title":"Methodology"},{"key":"2026070321250822000_2026.06.26.734424v1.22","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.53715"},{"issue":"1","key":"2026070321250822000_2026.06.26.734424v1.23","doi-asserted-by":"crossref","first-page":"39","DOI":"10.2307\/3315656","article-title":"Tables for the friedman rank test","volume":"21","year":"1993","journal-title":"Canadian Journal of Statistics"},{"key":"2026070321250822000_2026.06.26.734424v1.24","doi-asserted-by":"publisher","DOI":"10.1207\/s15327574ijt0502_4"},{"key":"2026070321250822000_2026.06.26.734424v1.25","first-page":"1","article-title":"FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data","volume":"2011","year":"2011","journal-title":"Computational Intelligence and Neuroscience"},{"key":"2026070321250822000_2026.06.26.734424v1.26","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/21\/R271"},{"key":"2026070321250822000_2026.06.26.734424v1.27","doi-asserted-by":"crossref","first-page":"101972","DOI":"10.1016\/j.nicl.2019.101972","article-title":"Aberrant MEG multi-frequency phase temporal synchronization predicts conversion from mild cognitive impairment-to-Alzheimer\u2019s disease","volume":"24","year":"2019","journal-title":"NeuroImage: Clinical"},{"key":"2026070321250822000_2026.06.26.734424v1.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2010.01.008"},{"key":"2026070321250822000_2026.06.26.734424v1.29","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2317881"},{"key":"2026070321250822000_2026.06.26.734424v1.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118331"},{"key":"2026070321250822000_2026.06.26.734424v1.31","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nemann, P. H. (1966). A Generalized Solution of the Orthogonal Procrustes Problem. Psychometrika, 31(1):1\u201310. Publisher: Cambridge University Press (CUP).","DOI":"10.1007\/BF02289451"},{"issue":"1","key":"2026070321250822000_2026.06.26.734424v1.32","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1038\/s42003-024-06829-8","article-title":"Fingerprints of brain disease: connectome identifiability in Alzheimer\u2019s disease","volume":"7","year":"2024","journal-title":"Communications Biology"},{"key":"2026070321250822000_2026.06.26.734424v1.33","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0978"},{"key":"2026070321250822000_2026.06.26.734424v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.05.041"},{"key":"2026070321250822000_2026.06.26.734424v1.35","doi-asserted-by":"publisher","DOI":"10.1002\/ana.252B9"},{"issue":"1","key":"2026070321250822000_2026.06.26.734424v1.36","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1038\/s41467-018-05316-z","article-title":"Spontaneous cortical activity transiently organises into frequency specific phase-coupling networks","volume":"9","year":"2018","journal-title":"Nature Communications"},{"issue":"12","key":"2026070321250822000_2026.06.26.734424v1.37","doi-asserted-by":"crossref","first-page":"3259","DOI":"10.1109\/TIFS.2019.2916403","article-title":"Convolutional neural networks using dynamic functional connectivity for eeg-based person identification in diverse human states","volume":"14","year":"2019","journal-title":"IEEE Transactions on Information Forensics and Security"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.26.734424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:25:42Z","timestamp":1783139142000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.06.26.734424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.64898\/2026.06.26.734424","relation":{},"subject":[],"published":{"date-parts":[[2026,7,1]]},"subtype":"preprint"}}